Geo Measure Agent Skill

Measure GEO visibility from an approved, file-backed engine observation bundle. Use for AI answer mention rate, source inclusion, citation share, query-panel coverage, GEO monitoring, 监测 AI 可见度, 衡量 GEO 效果, and offline baseline comparison. Exclude live scraping, platform login, automated collection, and unsupported causal claims.

3k tokens

context cost

the whole folder, loaded on every use

files

ships runnable scripts

copies elsewhere

how many repositories repackaged it

101

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/yaojingang/GEOHub --skill geo-measure

What comes with it

12 485 bytes besides the instruction

agents/interface.yaml

evals/output/cases.jsonl

evals/semantic_config.json

evals/trigger_cases.json

manifest.json

references/input-example.json

references/measurement-method.md

references/output-contract.md

reports/output_quality_scorecard.md

reports/skill-ir.json

reports/trust-report.md

scripts/run_measure.py

The instruction itself

4 sections, as written by the author

GEO Measure

Workflow

Read references/measurement-method.md and verify collection permission.
Prepare a protocol 1.0.0 engine observation bundle from manual export, approved API, or recorded fixture.
Run python3 scripts/run_measure.py --input <bundle.json> --output <runs-root>.
Inspect visibility-report.json, quality-report.json, and run-lineage.json; surface every gap and collection limitation.
Deliver the Artifact Bus run directory as the output contract.

Output contract

Produce the input snapshot, visibility-report.json, quality-report.json, run-lineage.json, and run-manifest.json. Preserve query-level components, per-engine metrics, numerators, denominators, missing counts, panel version, and semantic digest.

Boundaries

Measurement is offline and file-backed. It never logs in, scrapes consumer AI pages, bypasses access controls, or turns recorded fixtures into live-effect evidence. Read references/output-contract.md before making a comparison claim.

How to use it

Copy the folder

Take yaojingang/geo-measure from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.